Syntax - Tasty Web Development Treats18 Joulu 2023

706: AI and ML - The Pieces Explained

In this episode of Syntax, Wes and Scott talk about understanding the integration of different components in AI models, the choice between traditional models and Language Learning Models (LLM), the relevance of the Hugging Face library, demystify Llama, discuss spaces in AI, and highlight available services. Show Notes 00:25:20 Welcome 00:55:00 Syntax Brought to you by Sentry 01:17:00 Understanding how the pieces fit together 02:31:18 Models or LLM? 04:43:22 What about Hugging Face? 08:05:18 What’s Llama? 08:51:15 What are spaces? 09:29:06 Services available to you 12:26:16 What are tokens in AI? 17:38:18 What is temperature with AI? 20:33:08 Using top_p 21:06:00 Using fine-tuning to extend existing models 22:11:19 Prompts are what you send to the model 23:17:00 Streaming 24:48:17 Embeddings 27:34:17 OpenAI maintains Evals 28:40:14 Different libraries for working with AI Hugging Face Creator of Swift, Tesla Autopilot & Tensorflow. New AI language Mojo with Chris Lattner LLaMA Spaces - Hugging Face OpenAI Anthropic \ Introducing Claude Replicate Fireworks Console gpt-tokenizer playground openai/tiktoken: tiktoken is a fast BPE tokeniser for use with OpenAI’s models. Supper Club × OpenAI, Future of programming, LLMs, and Math with Andrey Mishchenko Raycast Pro Amazon SageMaker (AMS SSPS) openai/evals LangChain PyTorch TensorFlow ai - npm Hit us up on Socials! Syntax: X Instagram Tiktok LinkedIn Threads Wes: X Instagram Tiktok LinkedIn Threads Scott: X Instagram Tiktok LinkedIn Threads

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(1050)

1050 - Everyone Is Hacking Their TV

Wes, Scott, and CJ run through the week’s biggest web dev news: everyone’s hacking their TVs, VoidZero open-sourced its Void framework with Cloudflare deploys, OpenCode got hacked, and Anthropic built...

26 Loka 1h 19min

1049: WTF is a Software Factory?

Scott and Wes talk with Adam Jacob about software factories: what they actually are, why they’re unique to each team, and how to build trust in agent-generated code. They dig into Swamp Club, black bo...

21 Loka 57min

1048: Deno Is Dead

Deno is shutting down and the team is heading to Cloudflare — Scott, Wes, and CJ break down what that means for the runtime, JSR, and workerd. Plus OpenCode 2.0 on durable objects, TanStack Start 1.0,...

19 Loka 1h 40min

1047: Adobe has a big problem

Someone just clean-room ported seven Adobe apps to Rust, and Wes is shocked at how good it is. Scott and Wes break down what it gets right, what’s still missing, and why copying software is easy but i...

14 Loka 35min

1046: The Pi Updates are insane

Scott, Wes, and CJ break down the latest Pi updates, including durable long-running agents, Codemode, and MCP support, then debate whether pull requests are dead in favor of issues. Plus Supabase pick...

12 Loka 1h 40min

1045: Who can actually max out 5 AI subscriptions?

Scott and Wes answer listener questions about what replaced blogging, what to do while your AI agent works, and who should pay for token costs. They also cover keeping agents from going off the rails,...

7 Loka 52min

1044: Ruby on Rails is Dead

Scott, Wes, and CJ ask whether Ruby on Rails is really dead (and whether Rust is just Rails you don't have to read), then dig into Meta's new Muse agent, which is free, comes with its own VM, and is a...

5 Loka 1h 20min

1043: I’m Using GPUI For Everything

Scott and Wes ditch Electron and Tauri for GPUI, the GPU accelerated Rust UI framework from the Zed team. They get into its React-like API, styling that feels a lot like Tailwind, GPUI Kit components,...

30 Syys 32min